Vision inspection system and method of inspecting parts

Abstract

A vision inspection system includes a sorting platform having an upper surface supporting parts for inspection. An inspection station is positioned adjacent the sorting platform including an imaging device to image the parts in a field of view. A vision inspection controller receives images from the imaging device. The vision inspection controller includes an image histogram tool to pre-process the images to improve contrast of the images by redistributing lightness values of the images based on adaptive histogram equalization processing to generate enhanced images. The vision inspection controller processes the enhanced images based on an image analysis model to determine inspection results for each of the parts. The vision inspection controller has an artificial intelligence learning module operated to customize and configure the image analysis model based on the enhanced images.

Description

CROSS REFERENCE TO RELATED APPLICATIONS[0001]This application claims benefit to Chinese Application No. 202010493394.4, filed 3 Jun. 2020, the subject matter of which is herein incorporated by reference in its entirety.BACKGROUND OF THE INVENTION[0002]The subject matter herein relates generally to vision inspection systems.[0003]Inspection systems are used for inspecting parts during a manufacturing process. Conventional inspection systems use personnel to manually inspect parts, such as to identify defective parts. Such manual inspection systems are labor intensive and high cost. The manual inspection systems have low detection accuracy leading to poor product consistency. Additionally, manual inspection systems suffer from human error due to fatigue, such as missed defects, wrong counts, misplacing of parts, and the like. Some known inspection systems use machine vision for inspecting parts. The machine vision inspection systems use cameras to image the parts. Image quality is a p...

AI Technical Summary

Benefits of technology

[0005]In one embodiment, a vision inspection system is provided. The vision inspection system includes a sorting platform having an upper surface supporting parts for inspection. An inspection station is positioned adjacent the sorting platform. The inspection station includes an imaging device to image the parts in a field of view above the upper surface. A vision inspection controller receives images from the imaging device. The vision inspection controller includes an image histogram tool to pre-process the images to improve contrast of the images by redistributing lightness values of the images based on adaptive histogram equalization processing to generate enhanced images. The vision inspection controller processes the enhanced images based on an image analysis model to determine inspection results for each of the parts. The vision inspection controller has an artificial intelligence learning module operated to customize and configure the image analysis model based on the enhanced images.

[0006]In another embodiment, a vision inspection system is provided. The vision inspection system includes a sorting platform having an upper surface supporting parts for inspection. An inspection station is positioned adjacent the sorting platform. The inspection station includes an imaging device to image the parts in a field of view above the upper surface. A vision inspection controller receives images from the imaging device. The vision inspection controller includes an image histogram tool pre-processing the images to improve contrast of the images. The image histogram tool generates a histogram. The image histogram tool computes a cumulative distribution function based on the histogram. The image histogram tool calculates enhanced lightness values of the images based on the cumulative distribution function to generate enhanced images. The vision inspection controller includes a shape recognition tool processing the enhanced images based on an image analysis module to determine inspection results for each of the parts. The vision inspection controller has an artificial intelligence learning module operated to customize and configure the image analysis model based on the enhanced images.

[0007]In a further embodiment, a method of inspecting parts is provided. The method loads the parts on an upper surface of a sorting platform. The method images the parts at an inspection station positioned adjacent the sorting platform using an imaging device to image the parts on the upper surface. The method receives images from the imaging device at a vision inspection controller having an image histogram tool and a shape recognition tool. The method pre-processes the images using the image histogram tool to improve contrast of the images by redistributing lightness values of the images based on adaptive histogram equalization processing to generate enhanced images. The method processes the enhanced images using the shape recognition tool based on an image analysis module to determine inspection results for each of the parts and customizes the image analysis model using an artificial intelligence learning module to configure the image analysis model based on the enhanced images.

Problems solved by technology

Such manual inspection systems are labor intensive and high cost.

The manual inspection systems have low detection accuracy leading to poor product consistency.

Additionally, manual inspection systems suffer from human error due to fatigue, such as missed defects, wrong counts, misplacing of parts, and the like.

Image quality is a problem with known machine vision inspection systems.

For example, poor image quality due to poor image contrast, poor image brightness, and the like result in poor system performance and faulty inspection.

However, imaging the parts multiple times results in slow throughput.

Images